List your company

Agent Task Completion and Safety on AgentDojo Banking stock (test)

65.97UtilityLACUNA
52.273255.829159.38562.9409May 27, 2026

Evaluation results

MethodLinks
LACUNAModel=o4-mini-high2026.0565.970
LACUNAModel=gemini-2.5-pro2026.0563.190
CaMeLModel=o4-mini-high2026.0562.51
TACITModel=o4-mini-high2026.0559.030
TACITModel=gemini-2.5-pro2026.0556.940
CaMeLModel=gemini-2.5-pro2026.0552.80